R Notebook

library(tidyverse)

Registered S3 methods overwritten by 'dbplyr':
  method         from
  print.tbl_lazy     
  print.tbl_sql      
── Attaching packages ─────────────────────────────────────────────────────────────────────────────────────── tidyverse 1.3.1 ──
✓ ggplot2 3.3.5     ✓ purrr   0.3.4
✓ tibble  3.1.6     ✓ dplyr   1.0.6
✓ tidyr   1.1.3     ✓ stringr 1.4.0
✓ readr   1.4.0     ✓ forcats 0.5.1
── Conflicts ────────────────────────────────────────────────────────────────────────────────────────── tidyverse_conflicts() ──
x dplyr::filter() masks stats::filter()
x dplyr::lag()    masks stats::lag()

library(plotly)

Registered S3 method overwritten by 'data.table':
  method           from
  print.data.table     
Registered S3 methods overwritten by 'htmltools':
  method               from         
  print.html           tools:rstudio
  print.shiny.tag      tools:rstudio
  print.shiny.tag.list tools:rstudio
Registered S3 method overwritten by 'htmlwidgets':
  method           from         
  print.htmlwidget tools:rstudio

Attaching package: ‘plotly’

The following object is masked from ‘package:ggplot2’:

    last_plot

The following object is masked from ‘package:stats’:

    filter

The following object is masked from ‘package:graphics’:

    layout

library(rcartocolor)

merged <- read_tsv('../output/merged_table.tsv')

── Column specification ────────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  Specialty = col_character(),
  `No. of Programs` = col_double(),
  `Positions Offered` = col_number(),
  `Unfilled Programs` = col_double(),
  `MD Senior Applicants` = col_number(),
  `Total Applicants` = col_number(),
  `MD Senior Matches` = col_number(),
  `Total Matches` = col_number(),
  `MD Senior % Filled` = col_double(),
  `Total % Filled` = col_double(),
  `MD Senior Ranked Positions` = col_number(),
  `Total Ranked Positions` = col_character(),
  Year = col_double(),
  Class = col_character()
)

merged %>% 
  filter(Specialty == 'Dermatology') 

long_table_absolute <- merged %>% 
  select(Specialty,
         Year,
         Class,
         `Positions Offered`,
         `MD Senior Applicants`,
         `Total Applicants`,
         `MD Senior Matches`,
         `Total Matches`) %>% 
  pivot_longer(cols = -c(Specialty, Year, Class),
               names_to = 'Name',
               values_to = 'Value') %>% 
  arrange(Specialty, Class, Year)

long_table_absolute

long_table_percent <-  merged %>% 
  select(Specialty,
         Year,
         Class, 
         `MD Senior % Filled`,
         `Total % Filled`) %>% 
  pivot_longer(cols = -c(Specialty, Year, Class),
               names_to = 'Name',
               values_to = 'Value') %>% 
  arrange(Specialty, Class, Year)

long_table_percent 

p <- long_table_absolute %>% 
  filter(Specialty == 'Dermatology', Class == 'PGY2') %>% 
  ggplot(aes(x = Year,
             y = Value,
             color = Name)) +
  geom_point() +
  geom_line() + 
  facet_wrap(~Specialty + Class, scales = 'free_y') +
  theme_bw() +
  scale_color_carto_d(palette = 'Bold') 

p

input <- 'Dermatology'
plot_data <- merged %>% filter(Specialty == input,
                                Class == 'PGY2')#long_table_absolute %>% filter(Specialty == 'Dermatology')

fig <- plot_ly(plot_data, x = ~Year)
fig <- fig %>% add_trace(y = ~`Positions Offered`, name = 'Positions Offered', mode = 'lines+markers')
fig <- fig %>% add_trace(y = ~`MD Senior Applicants`, name = 'MD Senior Applicants', mode = 'lines+markers')
fig <- fig %>% add_trace(y = ~`Total Applicants`, name = 'Total Applicants', mode = 'lines+markers')

fig %>%
  layout(                        # all of layout's properties: /r/reference/#layout
    title = input, # layout's title: /r/reference/#layout-title
    xaxis = list(           # layout's xaxis is a named list. List of valid keys: /r/reference/#layout-xaxis
      title = "Time",      # xaxis's title: /r/reference/#layout-xaxis-title
      showgrid = F),       # xaxis's showgrid: /r/reference/#layout-xaxis-showgrid
    yaxis = list(           # layout's yaxis is a named list. List of valid keys: /r/reference/#layout-yaxis
      title = "uidx")     # yaxis's title: /r/reference/#layout-yaxis-title
  )

No trace type specified:
  Based on info supplied, a 'scatter' trace seems appropriate.
  Read more about this trace type -> https://plotly.com/r/reference/#scatter
No trace type specified:
  Based on info supplied, a 'scatter' trace seems appropriate.
  Read more about this trace type -> https://plotly.com/r/reference/#scatter
No trace type specified:
  Based on info supplied, a 'scatter' trace seems appropriate.
  Read more about this trace type -> https://plotly.com/r/reference/#scatter
No trace type specified:
  Based on info supplied, a 'scatter' trace seems appropriate.
  Read more about this trace type -> https://plotly.com/r/reference/#scatter
No trace type specified:
  Based on info supplied, a 'scatter' trace seems appropriate.
  Read more about this trace type -> https://plotly.com/r/reference/#scatter
No trace type specified:
  Based on info supplied, a 'scatter' trace seems appropriate.
  Read more about this trace type -> https://plotly.com/r/reference/#scatter

p <- long_table_absolute %>% 
  filter(Specialty == 'Dermatology') %>% 
  ggplot(aes(x = Year,
             y = Value,
             color = Name)) +
  geom_point() +
  geom_line() + 
  facet_wrap(~Specialty + Class, scales = 'free_y') +
  theme_bw() +
  scale_color_carto_d(palette = 'Bold') 

ggplotly(p)

Export

long_table_absolute %>% write_tsv('../../analysis/output/long_table_absolute.tsv')
long_table_percent %>% write_tsv('../../analysis/output/long_table_percent.tsv')